Feature — Video generation

Three ways to generate a video that says every visitor's first name

Cloned AI voice, talking photo avatar or premium lip-sync: one engine turns quiz answers into a personalized video. Every visitor hears their first name, their answers quoted, and the offer built for them — generated in under a minute, with no studio and no filming.

The only platform whose video actually speaks the visitor's first name and echoes their answers — not just a text field pasted on screen.

to generate a video
~1 min
of audio to clone your voice
2 min
is enough for a talking avatar
1 photo
languages supported
25+

The pipeline

From quiz to personalized video in five automatic steps

The visitor finishes the quiz, the rest fires on its own. No manual step: the engine chains script, voice, avatar and render, then serves the video right in the browser.

  1. Quiz completed

    The visitor has shared their first name, email and answers. Scoring sorts them into a segment (beginner, premium, urgent…).

  2. AI script composed

    Your script template — written once — is filled by the AI: first name, goal, answers quoted word for word, and a CTA tailored to the segment.

  3. Voice generated

    Your cloned voice (or a synthetic one) speaks the script. The first name is said naturally, not pasted in post-production.

  4. Avatar animated

    Depending on the chosen mode: an animated background, a talking photo avatar, or your reference video re-synced to the new script.

  5. Video served

    The video plays in the visitor's browser, with their first name on screen, and stays available by link and by email.

Typical total time: 30 seconds to 1 minute. If the render runs long, the video is sent automatically by email — you never lose the lead.

The 3 modes

Choose your level of presence

The same differentiator in all three — the video says the first name and quotes the answers. What changes is the on-screen presence: from voice alone to lip-sync indistinguishable from a real shoot. Move up a tier when your conversions justify it.

Mode 1from Starter

Cloned AI voice

Your voice, over an animated visual in your colors

The most affordable and the fastest mode to set up. No image of you: your cloned voice speaks the personalized script over an animated background in your brand. Perfect to get started and validate the effect before moving up.

How it works

  • You record ~2 minutes of audio from your browser (or upload a file).
  • The AI creates a clone of your voice, reserved for your videos.
  • On every completed quiz, the clone reads the script and speaks the visitor's first name.
  • The voice sits over a customizable animated background (colors, logo, dynamic subtitles).

Who it's for

Coaches, trainers and e-commerce sellers who want to launch fast, at a controlled cost, and test video personalization without appearing on screen.

Mode 2from Growth

Talking photo avatar

A photo becomes your AI presenter — zero filming

The best effort-to-impact ratio. Upload a single photo: the AI (via HeyGen) animates it and makes it talk in your cloned voice. The “they're speaking to me” effect without ever filming yourself — no studio, no camera.

How it works

  • You upload a photo of yourself (or pick a presenter from our catalog).
  • The AI builds a talking avatar from that single image.
  • For each visitor, the avatar speaks the script with your cloned voice included.
  • Lips, expressions and gaze are synced to the personalized audio.

Who it's for

Experts who want a face and a human presence — coaches, consultants, practitioners — but have neither the time nor the wish to film every variant.

Mode 3from Scale

Premium lip-sync

Your real video, re-synced for every script

The most high-end output on the market. Film yourself once; the AI re-syncs your lips to every personalized script. The result is indistinguishable from a real shoot — your real image, your real gestures, a thousand variants.

How it works

  • You film a short reference video (just once).
  • For each visitor, the AI generates the personalized script and audio.
  • Your lips are re-synced in high fidelity to that new audio.
  • The rest of the image (set, gestures, gaze) stays your real footage.

Who it's for

Premium brands and agencies that demand broadcast quality and want to leverage the real image of their founder or expert, at scale.

The differentiator

The first name spoken, the answers quoted — not a field stuck on screen

Most tools insert a first name as a text overlay. Quiz Funnel goes further: the voice actually speaks the first name, and the script echoes the exact quiz answers. That's what competitor quizfunnel.app doesn't do — and it's what triggers attention.

  • The name is spoken, not displayed

    The cloned voice articulates the first name inside the sentence, in the right spot. No text overlay slapped on top of a generic video.

  • The answers are quoted

    The script echoes word for word what the visitor selected: their goal, their level, their budget. They feel understood, not labeled.

  • The segment drives the offer

    The quiz scoring picks the right CTA and the right offer. Every video closes on the next step most relevant to that profile.

“Hi Marie! You want to get back in shape before summer with 3 sessions a week — here's exactly where to start…”
Generated for each visitor, from THEIR answers.

Comparison

Which mode should you choose?

All three modes share the same differentiator — first name spoken, answers quoted. The table below sums up what sets them apart.

CritèreCloned AI voiceTalking photo avatarPremium lip-sync
Planfrom Starterfrom Growthfrom Scale
What you provide~2 min of audio1 photo + audio1 reference video
On-screen presenceVoice + animated bgTalking avatarYou, for real
Filming requiredNoneNoneOnce
First name spokenYesYesYes
Answers quotedYesYesYes
Output levelEfficientPremiumBroadcast
Best forLaunching fastA human face at scaleBrands & agencies

You can switch modes at any time, and even vary the mode per quiz. The differentiator — first name + answers — stays identical across all three.

Frequently asked questions about video generation

Everything we get asked about voice cloning, avatars and output quality. Another question? Write to us — we reply within 24 business hours.

How does voice cloning work?

You record about 2 minutes of audio from your browser, or upload an existing file. Our AI creates a replica of your voice used exclusively to generate YOUR videos. You sign explicit consent when the clone is created, and you can delete it permanently at any time from your dashboard.

Does the talking avatar need filming?

No. The Talking photo avatar mode only needs a single photo: the AI animates it and makes it speak the script with your cloned voice. No camera, no studio. Only the Premium lip-sync mode needs a short reference video, filmed once and then reused for thousands of variants.

How is this different from a first name shown on screen?

Most tools overlay a “{first_name}” text field on top of a video that's identical for everyone. With Quiz Funnel, the voice actually speaks the first name inside the sentence, and the script echoes the visitor's exact answers. It's a video built for them, not a generic video with a label stuck on it — which is precisely what competitor quizfunnel.app doesn't offer.

How long does it take to generate a video?

Usually between 30 seconds and 1 minute depending on the mode. Meanwhile, your visitor sees a personalized waiting screen with their first name. If generation runs past the expected delay, the video is sent automatically by email: you never lose the lead.

Which languages can the video speak?

Voice cloning and synthesis work in French, English and 25+ languages (Spanish, German, Italian, Portuguese…). Handy if your audience is international: each visitor can receive their video in their language.

Can I switch modes later?

Yes, at any time, and you can even use a different mode per quiz. You can start with AI Voice to validate the effect, then move to the Photo Avatar or Premium lip-sync when your conversions justify it. The differentiator — first name spoken and answers quoted — stays identical across all three modes.

Generate your first personalized video within the hour

Clone your voice in 2 minutes, upload a photo, or film yourself once. Whatever the mode, each visitor will get a video that says their first name and echoes their answers.

  • 14 days free
  • No credit card
  • GDPR compliant
AI video generation: cloned voice, talking photo avatar & lip-sync · Quiz Funnel